{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:XA4BKXCLY6OASQ73TAW45CHHAJ","short_pith_number":"pith:XA4BKXCL","schema_version":"1.0","canonical_sha256":"b838155c4bc79c0943fb982dce88e70261d142f198adeaf18642034e27d1a3dd","source":{"kind":"arxiv","id":"1703.03123","version":2},"attestation_state":"computed","paper":{"title":"Scaling up Data Augmentation MCMC via Calibration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"David B. Dunson, James E. Johndrow, Leo L. Duan","submitted_at":"2017-03-09T03:49:33Z","abstract_excerpt":"There has been considerable interest in making Bayesian inference more scalable. In big data settings, most literature focuses on reducing the computing time per iteration, with less focused on reducing the number of iterations needed in Markov chain Monte Carlo (MCMC). This article focuses on data augmentation MCMC (DA-MCMC), a widely used technique. DA-MCMC samples tend to become highly autocorrelated in large data samples, due to a miscalibration problem in which conditional posterior distributions given augmented data are too concentrated. This makes it necessary to collect very long MCMC "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1703.03123","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2017-03-09T03:49:33Z","cross_cats_sorted":[],"title_canon_sha256":"05eff70ce44892596fbc945f0fea2289bd09f0b00a395f1f14bcfe8d7e939156","abstract_canon_sha256":"d44a08fa1ba2016931cc41d6f6d41855ddfcb3db7ba73b836877980036a1289d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:15.386713Z","signature_b64":"TDebqJZ0MmZbKXW1F/SC++zY1WhFAwmX4o4g9JKDZxdyQUDHVIywxAoB/pw7Vac+lTSvj4XKe77bENxsVPYaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b838155c4bc79c0943fb982dce88e70261d142f198adeaf18642034e27d1a3dd","last_reissued_at":"2026-05-18T00:34:15.386069Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:15.386069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling up Data Augmentation MCMC via Calibration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"David B. Dunson, James E. Johndrow, Leo L. Duan","submitted_at":"2017-03-09T03:49:33Z","abstract_excerpt":"There has been considerable interest in making Bayesian inference more scalable. In big data settings, most literature focuses on reducing the computing time per iteration, with less focused on reducing the number of iterations needed in Markov chain Monte Carlo (MCMC). This article focuses on data augmentation MCMC (DA-MCMC), a widely used technique. DA-MCMC samples tend to become highly autocorrelated in large data samples, due to a miscalibration problem in which conditional posterior distributions given augmented data are too concentrated. This makes it necessary to collect very long MCMC "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.03123","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1703.03123","created_at":"2026-05-18T00:34:15.386179+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.03123v2","created_at":"2026-05-18T00:34:15.386179+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.03123","created_at":"2026-05-18T00:34:15.386179+00:00"},{"alias_kind":"pith_short_12","alias_value":"XA4BKXCLY6OA","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"XA4BKXCLY6OASQ73","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"XA4BKXCL","created_at":"2026-05-18T12:31:53.515858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XA4BKXCLY6OASQ73TAW45CHHAJ","json":"https://pith.science/pith/XA4BKXCLY6OASQ73TAW45CHHAJ.json","graph_json":"https://pith.science/api/pith-number/XA4BKXCLY6OASQ73TAW45CHHAJ/graph.json","events_json":"https://pith.science/api/pith-number/XA4BKXCLY6OASQ73TAW45CHHAJ/events.json","paper":"https://pith.science/paper/XA4BKXCL"},"agent_actions":{"view_html":"https://pith.science/pith/XA4BKXCLY6OASQ73TAW45CHHAJ","download_json":"https://pith.science/pith/XA4BKXCLY6OASQ73TAW45CHHAJ.json","view_paper":"https://pith.science/paper/XA4BKXCL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.03123&json=true","fetch_graph":"https://pith.science/api/pith-number/XA4BKXCLY6OASQ73TAW45CHHAJ/graph.json","fetch_events":"https://pith.science/api/pith-number/XA4BKXCLY6OASQ73TAW45CHHAJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XA4BKXCLY6OASQ73TAW45CHHAJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XA4BKXCLY6OASQ73TAW45CHHAJ/action/storage_attestation","attest_author":"https://pith.science/pith/XA4BKXCLY6OASQ73TAW45CHHAJ/action/author_attestation","sign_citation":"https://pith.science/pith/XA4BKXCLY6OASQ73TAW45CHHAJ/action/citation_signature","submit_replication":"https://pith.science/pith/XA4BKXCLY6OASQ73TAW45CHHAJ/action/replication_record"}},"created_at":"2026-05-18T00:34:15.386179+00:00","updated_at":"2026-05-18T00:34:15.386179+00:00"}